NousResearch/hermes-agent

OpenRouter prompt-injection 403 misclassified; content-policy handling and session guidance

Cluster 132504 · agent. Data as of

2 open items. Fix attempted, not merged.

The short answer

1open issue
1open PR
3items grouped
Known?
Yes. 3 related items grouped here, 0 issues already closed.
Fix event
No fix has been merged to main. 1 PR closed without merging; see the attempts below.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
1 issue and 1 PR.

The members center on OpenRouter returning a 403 for 'prompt injection patterns detected' when bundled skills contain <tool>, which is reportedly mislabelled as a firewall block and affects the session. Two related pull requests concern classifying this response as content_policy_blocked and directing blocked turns toward a new session rather than a reword.

Open issues1

  • Issue#132504OpenRouter 403 "prompt injection patterns detected" from bundled skills containing <tool> — mislabelled as a firewall block, and it poisons the whole session

Open PRs1

  • PR#132643fix(agent): classify OpenRouter's prompt-injection guardrail 403 as content_policy_blocked

1 PR closed without merging

From the close comments: closed without comment 1

  • #136254 fix(content-policy): point blocked turns at a new session, not a reword · closed without comment
How this cluster was grouped
  • Link evidence (structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
  • Pairwise link density 0.67: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. 1.00 means every pair is linked.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Subsystem
agent
Closed issues
0
Attempts
1 PR closed without merging

For your agent

The same facts, typed.